// the following loop takes half of a microsecond (4 cycles)
    // per iteration, so execute it twice for each microsecond of
    // delay requested.
    us <<= 1;

    // busy wait
    __asm__ __volatile__ (
        "1: sbiw %0,1" "\n\t" // 2 cycles
        "brne 1b" : "=w" (us) : "0" (us) // 2 cycles
    );